
import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt
import plotly.express as px

import nltk
import re
from nltk.stem import WordNetLemmatizer

from sklearn.feature_extraction.text import CountVectorizer
from sklearn.model_selection import train_test_split

from sklearn.naive_bayes import MultinomialNB

from sklearn.metrics import classification_report
from sklearn.metrics import confusion_matrix


# Importing dataset
review = pd.read_csv(r"E:\HASAN\WLU UNIVERSITY\1st Semester (FALL)\CP-640 - Machine Learning\Project\Womens Clothing E-Commerce Reviews.csv")
review.head()


# Deleting first unnamed column
review = review.loc[:, ~review.columns.str.contains('^Unnamed')]
review.head()


# Checking null value
review.isnull().sum()

Clothing ID                   0
Age                           0
Title                      3810
Review Text                 845
Rating                        0
Recommended IND               0
Positive Feedback Count       0
Division Name                14
Department Name              14
Class Name                   14
dtype: int64


# Deleting null values because it is less than 30% of whole data
review = review.dropna(axis=0)


# Checking null value after removing
review.isnull().sum()

Clothing ID                0
Age                        0
Title                      0
Review Text                0
Rating                     0
Recommended IND            0
Positive Feedback Count    0
Division Name              0
Department Name            0
Class Name                 0
dtype: int64


# Shows that there are 19662 rows and 10 columns
review.shape

(19662, 10)


# Shows datatype of each column
review.dtypes

Clothing ID                 int64
Age                         int64
Title                      object
Review Text                object
Rating                      int64
Recommended IND             int64
Positive Feedback Count     int64
Division Name              object
Department Name            object
Class Name                 object
dtype: object


# Shows count, mean, standard deviation, minimum, maximum, 25% 50% 75% percentiles
review.describe()


review.describe(include=object)


print(review.groupby('Age').size())

Age
18      4
19     28
20     91
21     75
22    106
     ... 
91      3
92      1
93      2
94      1
99      1
Length: 77, dtype: int64


sns.histplot(review['Age'])
plt.title('Count of Age of Reviewer')
plt.show()


ri = review.groupby('Recommended IND').size()
print(ri)

Recommended IND
0     3575
1    16087
dtype: int64


ri_labels = ['Not Recommended', 'Recommended']
plt.pie(ri, labels=ri_labels, autopct='%.1f%%')
plt.title('Number of Positive and Negative Reviews')
plt.legend()
plt.show()


print(review.groupby('Division Name').size())

Division Name
General           11664
General Petite     6778
Initmates          1220
dtype: int64


sns.countplot(x = review['Division Name'])
plt.title('Number of Different Divisions')
plt.show()


rdn = review.groupby('Department Name').size()
print(rdn)

Department Name
Bottoms     3184
Dresses     5371
Intimate    1408
Jackets      879
Tops        8713
Trend        107
dtype: int64


rdn_labels = review['Department Name'].unique()
plt.pie(rdn, labels=rdn_labels, autopct='%.1f%%')
plt.title('Number of Different Department')
plt.legend()
plt.show()


print(review.groupby('Class Name').size())

Class Name
Blouses           2587
Casual bottoms       1
Chemises             1
Dresses           5371
Fine gauge         927
Intimates          120
Jackets            598
Jeans              970
Knits             3981
Layering           115
Legwear            131
Lounge             574
Outerwear          281
Pants             1157
Shorts             260
Skirts             796
Sleep              174
Sweaters          1218
Swim               293
Trend              107
dtype: int64


sns.countplot(x = review['Class Name'])
plt.xticks(rotation=90)
plt.title('Number of Different Classes')
plt.show()


rr = review.groupby('Rating').size()
print(rr)

Rating
1      691
2     1360
3     2464
4     4289
5    10858
dtype: int64


rr_labels = review['Rating'].unique()
plt.pie(rr, labels=rr_labels, autopct='%.1f%%')
plt.title('Number of Rating from 1 to 5')
plt.legend()
plt.show()


print(review.groupby('Positive Feedback Count').size())

Positive Feedback Count
0      8930
1      3502
2      1923
3      1258
4       803
       ... 
95        1
98        1
99        1
108       1
122       1
Length: 79, dtype: int64


sns.set(rc = {'figure.figsize':(18,5)})
sns.countplot(x = review['Positive Feedback Count'], label="Number of Visitors")
plt.xticks(rotation=90)
plt.title('Number of Positive Feedbacks')
plt.show()


g = sns.catplot(data = review, x ="Rating", hue = "Recommended IND", kind='count', height=7, aspect=2.5, legend_out=False)

plt.title('Rating Distribution By Recommendation', fontsize=26)
plt.xlabel("Rating", fontsize=20)
plt.ylabel("Number of Recommendations", fontsize=20)
plt.legend(title='Recommendation Indicator', loc='upper left', labels=['Not Recomnended', 'Recomnended'], fontsize='x-large', title_fontsize='24')

ax = g.facet_axis(0, 0)
for p in ax.patches:
    ax.text(p.get_x() + 0.12, 
            p.get_height() * 1.025, 
            '{0:.0f}'.format(p.get_height()), 
            color='black', rotation='horizontal', size='large')

plt.show()


review['Title'].loc[510]

'Gorgeous, flattering blouse!'


review['Review Text'].loc[51]

'I absolutely love this bib tee! it\'s probably my favorite retailer purchase of all time. i\'m 5\'7", 140 pounds and the small was a perfect fit for me. i typically wear either a s or m tops.'


words = review['Review Text'].str.split(expand=True).stack().value_counts()
words200 = words[:200]
fig = px.treemap(words200, path=[words200.index], values=0, width=900, height=900)
fig.update_layout(title_text='Top Frequent 200 Words in Review Text (Before Processing)')
fig.update_traces(textinfo="label+value")
fig.show()


# Removing Special Characters in Sentence
# ^ (Do Not  match) \w (alphanumeric characters) and \s (white space and tab)
def removing_special_character(text):
    new_text = re.sub('[^\w\s]','', text)
    return new_text

# Tokenizing Sentence with all lower case
def tokenize_sentence(text):
    text_tokens = nltk.word_tokenize(text.lower())
    return text_tokens

# Removing Numbers from text sentence
def removing_numbers(text):
    new_text = [x for x in text if x.isalpha()]
    return new_text

# Removing Stopwords from text sentence
def removing_stopwords(text):
    stopwords = nltk.corpus.stopwords.words("english")
    new_text = [x for x in text if x not in stopwords]
    return new_text

# Lemmatizing Sentence
def lemmatizer(text):
    new_text = [WordNetLemmatizer().lemmatize(x) for x in text]
    return new_text

# Joining the Tokenized Sentences
def join_token(text):
     return " ".join(text)


review['Title'] = review['Title'].apply(removing_special_character)


review['Title'] = review['Title'].apply(tokenize_sentence)


review['Title'] = review['Title'].apply(removing_numbers)


review['Title'] = review['Title'].apply(removing_stopwords)


review['Title'] = review['Title'].apply(lemmatizer)


review['Title'] = review['Title'].apply(join_token)


review['Review Text'] = review['Review Text'].apply(removing_special_character)


review['Review Text'] = review['Review Text'].apply(tokenize_sentence)


review['Review Text'] = review['Review Text'].apply(removing_numbers)


review['Review Text'] = review['Review Text'].apply(removing_stopwords)


review['Review Text'] = review['Review Text'].apply(lemmatizer)


review['Review Text'] = review['Review Text'].apply(join_token)


review['Title'].loc[510]

'gorgeous flattering blouse'


review['Review Text'].loc[51]

'absolutely love bib tee probably favorite retailer purchase time im pound small perfect fit typically wear either top'


words = review['Review Text'].str.split(expand=True).stack().value_counts()
words200 = words[:200]
fig = px.treemap(words200, path=[words200.index], values=0, width=900, height=900)
fig.update_layout(title_text='Top Frequent 200 Words in Review Text (After Processing)')
fig.update_traces(textinfo="label+value")
fig.show()


positive = review[review['Recommended IND']==1].copy()

positive_words = positive['Review Text'].str.split(expand=True).stack().value_counts()
words200 = positive_words[:200]
fig = px.treemap(words200, path=[words200.index], values=0, width=900, height=900)
fig.update_layout(title_text='Top Frequent 200 Positive Words in Review Text (After Processing)')
fig.update_traces(textinfo="label+value")
fig.show()


negative = review[review['Recommended IND']==0].copy()

negative_words = negative['Review Text'].str.split(expand=True).stack().value_counts()
words200 = negative_words[:200]
fig = px.treemap(words200, path=[words200.index], values=0, width=900, height=900)
fig.update_layout(title_text='Top Frequent 200 Negative Words in Review Text (After Processing)')
fig.update_traces(textinfo="label+value")
fig.show()


X1 = review["Review Text"]
Y1 = review["Recommended IND"]


# splitting test train data
X1_train, X1_test, Y1_train, Y1_test = train_test_split(X1, Y1, test_size=0.2)

print('Training Set:\tX1_train: ', X1_train.shape, ', Y1_train: ', Y1_train.shape, 
      '\nTesting Set:\tX1_test: ', X1_test.shape, ', Y1_test: ', Y1_test.shape)

Training Set:	X1_train:  (15729,) , Y1_train:  (15729,) 
Testing Set:	X1_test:  (3933,) , Y1_test:  (3933,)


vectorizer = CountVectorizer()

X1_train = vectorizer.fit_transform(X1_train)
X1_test = vectorizer.transform(X1_test)


nb = MultinomialNB()
nb.fit(X1_train, Y1_train)

nb_predict1 = nb.predict(X1_test)

print('Accuracy of Naive Bayes: {:.2f}'.format(nb.score(X1_test, Y1_test)))

Accuracy of Naive Bayes: 0.89


# Confusion Matrix of Naive Bayes using testset output and predicted output
print('Confusion Matrix:')
print(confusion_matrix(Y1_test, nb_predict1))

# Classification Report of Naive Bayes using testset output and predicted output
print('\nClassification Report:')
print(classification_report(Y1_test, nb_predict1))

Confusion Matrix:
[[ 415  305]
 [ 143 3070]]

Classification Report:
              precision    recall  f1-score   support

           0       0.74      0.58      0.65       720
           1       0.91      0.96      0.93      3213

    accuracy                           0.89      3933
   macro avg       0.83      0.77      0.79      3933
weighted avg       0.88      0.89      0.88      3933


r2 = review.loc[review['Positive Feedback Count'] > 1]
X2 = r2['Review Text']
Y2 = r2['Recommended IND']


# splitting test train data
X2_train, X2_test, Y2_train, Y2_test = train_test_split(X2, Y2, test_size=0.2)

print('Training Set:\tX2_train: ', X2_train.shape, ', Y2_train: ', Y2_train.shape, 
      '\nTesting Set:\tX2_test: ', X2_test.shape, ', Y2_test: ', Y2_test.shape)

Training Set:	X2_train:  (5784,) , Y2_train:  (5784,) 
Testing Set:	X2_test:  (1446,) , Y2_test:  (1446,)


vectorizer = CountVectorizer()

X2_train = vectorizer.fit_transform(X2_train)
X2_test = vectorizer.transform(X2_test)


nb = MultinomialNB()
nb.fit(X2_train, Y2_train)

nb_predict2 = nb.predict(X2_test)

print('Accuracy of Naive Bayes: {:.2f}'.format(nb.score(X2_test, Y2_test)))

Accuracy of Naive Bayes: 0.87


# Confusion Matrix of Naive Bayes using testset output and predicted output
print('Confusion Matrix:')
print(confusion_matrix(Y2_test, nb_predict2))

# Classification Report of Naive Bayes using testset output and predicted output
print('\nClassification Report:')
print(classification_report(Y2_test, nb_predict2))

Confusion Matrix:
[[ 158  144]
 [  44 1100]]

Classification Report:
              precision    recall  f1-score   support

           0       0.78      0.52      0.63       302
           1       0.88      0.96      0.92      1144

    accuracy                           0.87      1446
   macro avg       0.83      0.74      0.77      1446
weighted avg       0.86      0.87      0.86      1446


X3 = review['Title']
Y3 = review['Recommended IND']


# splitting test train data
X3_train, X3_test, Y3_train, Y3_test = train_test_split(X3, Y3, test_size=0.2)

print('Training Set:\tX3_train: ', X3_train.shape, ', Y3_train: ', Y3_train.shape, 
      '\nTesting Set:\tX3_test: ', X3_test.shape, ', Y3_test: ', Y3_test.shape)

Training Set:	X3_train:  (15729,) , Y3_train:  (15729,) 
Testing Set:	X3_test:  (3933,) , Y3_test:  (3933,)


vectorizer = CountVectorizer()

X3_train = vectorizer.fit_transform(X3_train)
X3_test = vectorizer.transform(X3_test)


nb = MultinomialNB()
nb.fit(X3_train, Y3_train)

nb_predict3 = nb.predict(X3_test)

print('Accuracy of Naive Bayes: {:.2f}'.format(nb.score(X3_test, Y3_test)))

Accuracy of Naive Bayes: 0.87


# Confusion Matrix of Naive Bayes using testset output and predicted output
print('Confusion Matrix:')
print(confusion_matrix(Y3_test, nb_predict3))

# Classification Report of Naive Bayes using testset output and predicted output
print('\nClassification Report:')
print(classification_report(Y3_test, nb_predict3))

Confusion Matrix:
[[ 362  347]
 [ 162 3062]]

Classification Report:
              precision    recall  f1-score   support

           0       0.69      0.51      0.59       709
           1       0.90      0.95      0.92      3224

    accuracy                           0.87      3933
   macro avg       0.79      0.73      0.76      3933
weighted avg       0.86      0.87      0.86      3933


r4 = review.loc[review['Positive Feedback Count'] > 1]
X4 = r4['Title']
Y4 = r4['Recommended IND']


# splitting test train data
X4_train, X4_test, Y4_train, Y4_test = train_test_split(X4, Y4, test_size=0.2)

print('Training Set:\tX4_train: ', X4_train.shape, ', Y4_train: ', Y4_train.shape, 
      '\nTesting Set:\tX4_test: ', X4_test.shape, ', Y4_test: ', Y4_test.shape)

Training Set:	X4_train:  (5784,) , Y4_train:  (5784,) 
Testing Set:	X4_test:  (1446,) , Y4_test:  (1446,)


vectorizer = CountVectorizer()

X4_train = vectorizer.fit_transform(X4_train)
X4_test = vectorizer.transform(X4_test)


nb = MultinomialNB()
nb.fit(X4_train, Y4_train)

nb_predict4 = nb.predict(X4_test)

print('Accuracy of Naive Bayes: {:.2f}'.format(nb.score(X4_test, Y4_test)))

Accuracy of Naive Bayes: 0.83


# Confusion Matrix of Naive Bayes using testset output and predicted output
print('Confusion Matrix:')
print(confusion_matrix(Y4_test, nb_predict4))

# Classification Report of Naive Bayes using testset output and predicted output
print('\nClassification Report:')
print(classification_report(Y4_test, nb_predict4))

Confusion Matrix:
[[ 126  187]
 [  52 1081]]

Classification Report:
              precision    recall  f1-score   support

           0       0.71      0.40      0.51       313
           1       0.85      0.95      0.90      1133

    accuracy                           0.83      1446
   macro avg       0.78      0.68      0.71      1446
weighted avg       0.82      0.83      0.82      1446


X5 = review[['Rating', 'Positive Feedback Count']]
Y5 = review['Recommended IND']


# splitting test train data
X5_train, X5_test, Y5_train, Y5_test = train_test_split(X5, Y5, test_size=0.2)

print('Training Set:\tX5_train: ', X5_train.shape, ', Y5_train: ', Y5_train.shape, 
      '\nTesting Set:\tX5_test: ', X5_test.shape, ', Y5_test: ', Y5_test.shape)

Training Set:	X5_train:  (15729, 2) , Y5_train:  (15729,) 
Testing Set:	X5_test:  (3933, 2) , Y5_test:  (3933,)


# vectorizer = CountVectorizer()

# X5_train = vectorizer.fit_transform(X5_train)
# X5_test = vectorizer.transform(X5_test)


nb = MultinomialNB()
nb.fit(X5_train, Y5_train)

nb_predict5 = nb.predict(X5_test)

print('Accuracy of Naive Bayes: {:.2f}'.format(nb.score(X5_test, Y5_test)))

Accuracy of Naive Bayes: 0.76


# Confusion Matrix of Naive Bayes using testset output and predicted output
print('Confusion Matrix:')
print(confusion_matrix(Y4_test, nb_predict4))

# Classification Report of Naive Bayes using testset output and predicted output
print('\nClassification Report:')
print(classification_report(Y4_test, nb_predict4))

Confusion Matrix:
[[ 126  187]
 [  52 1081]]

Classification Report:
              precision    recall  f1-score   support

           0       0.71      0.40      0.51       313
           1       0.85      0.95      0.90      1133

    accuracy                           0.83      1446
   macro avg       0.78      0.68      0.71      1446
weighted avg       0.82      0.83      0.82      1446

	Clothing ID	Age	Rating	Recommended IND	Positive Feedback Count
count	19662.000000	19662.000000	19662.000000	19662.000000	19662.000000
mean	921.297274	43.260808	4.183145	0.818177	2.652477
std	200.227528	12.258122	1.112224	0.385708	5.834285
min	1.000000	18.000000	1.000000	0.000000	0.000000
25%	861.000000	34.000000	4.000000	1.000000	0.000000
50%	936.000000	41.000000	5.000000	1.000000	1.000000
75%	1078.000000	52.000000	5.000000	1.000000	3.000000
max	1205.000000	99.000000	5.000000	1.000000	122.000000

	Unnamed: 0	Clothing ID	Age	Title	Review Text	Rating	Recommended IND	Positive Feedback Count	Division Name	Department Name	Class Name
0	0	767	33	NaN	Absolutely wonderful - silky and sexy and comf...	4	1	0	Initmates	Intimate	Intimates
1	1	1080	34	NaN	Love this dress! it's sooo pretty. i happene...	5	1	4	General	Dresses	Dresses
2	2	1077	60	Some major design flaws	I had such high hopes for this dress and reall...	3	0	0	General	Dresses	Dresses
3	3	1049	50	My favorite buy!	I love, love, love this jumpsuit. it's fun, fl...	5	1	0	General Petite	Bottoms	Pants
4	4	847	47	Flattering shirt	This shirt is very flattering to all due to th...	5	1	6	General	Tops	Blouses

	Title	Review Text	Division Name	Department Name	Class Name
count	19662	19662	19662	19662	19662
unique	13983	19656	3	6	20
top	Love it!	Perfect fit and i've gotten so many compliment...	General	Tops	Dresses
freq	136	3	11664	8713	5371

Removing First Unnamed Column¶

Checking Null Values¶

Removing Null Values¶

Checking Null Values After Removing¶

Number of Rows and Columns¶

Datatype of Each Columns¶

Describe Dataset¶

Count of Age of Reviewer¶

Number of Customer's Positive and Negative Recommendation¶

Number of Different Divisions¶

Number of Different Department¶

Number of Different Classes¶

Number of Customer's Rating from 1 to 5¶

Number of Positive Feedbacks¶

Rating Compared to Recommended or Not¶

Before Processing¶

Initializing Classes for Text Preparation¶

Processing Title Column¶

Processing Review Text Column¶

After Processing¶

Frequent Words in Positive Recommendation¶

Frequent Words in Negative Recommendation¶

Selecting Columns¶

Splitting Dataset into 80% Training Set and 20% Testing Set¶

Converting into Vectorize Form¶

Naive Bayes Multinomial¶

Classification Report and Confusion Matrix¶

Selecting Columns¶

Splitting Dataset into 80% Training Set and 20% Testing Set¶

Converting into Vectorize Form¶

Naive Bayes Multinomial¶

Classification Report and Confusion Matrix¶

Selecting Columns¶

Splitting Dataset into 80% Training Set and 20% Testing Set¶

Converting into Vectorize Form¶

Naive Bayes Multinomial¶

Classification Report and Confusion Matrix¶

Selecting Columns¶

Splitting Dataset into 80% Training Set and 20% Testing Set¶

Converting into Vectorize Form¶

Naive Bayes Multinomial¶

Classification Report and Confusion Matrix¶

Selecting Columns¶

Splitting Dataset into 80% Training Set and 20% Testing Set¶

Converting into Vectorize Form¶

Naive Bayes Multinomial¶

Classification Report and Confusion Matrix¶

Process¶